© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 30851
    Prev
    Next
    INDEX
    Explanations

    TripAdvisor, HomeAway, Corporation, Central

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ioc
    -0.09
    umer
    -0.09
    ÑģилÑĮ
    -0.09
    è¦ģéĹ»
    -0.09
    gross
    -0.09
    ANTED
    -0.09
    æݪ
    -0.08
     Ala
    -0.08
    peg
    -0.08
     molec
    -0.08
    POSITIVE LOGITS
     Zwe
    0.08
    éħĬ
    0.08
    ç¥ī
    0.08
    OrNull
    0.08
    /Public
    0.08
     Babies
    0.08
    娩
    0.08
    éĤ¸
    0.08
    æ¼Ĥ亮
    0.08
    è°¤
    0.08
    Activations Density 0.003%

    No Known Activations